main.py

import os
import torch
from fastapi import FastAPI
from transformers import AutoTokenizer, AutoModelForCausalLM
import uvicorn
from fastapi.middleware.cors import CORSMiddleware
app = FastAPI(docs_url="/")
app.add_middleware(
    CORSMiddleware,
    allow_origins=["*"],
    allow_methods=["*"],
    allow_headers=["*"],
)
tokenizer = AutoTokenizer.from_pretrained("succinctly/text2image-prompt-generator")
model = AutoModelForCausalLM.from_pretrained("succinctly/text2image-prompt-generator")
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
model.to(device)
model.eval()

@app.post("/text")
async def text(text: str):
    try:
        inputs = tokenizer(text, return_tensors="pt").to(device)
        outputs = model.generate(**inputs)
        
        generated_text = tokenizer.decode(outputs[0], skip_special_tokens=True)
        return {"generated_text": generated_text}
    except Exception as e:
        return {"error": str(e)}

if __name__ == "__main__":
    uvicorn.run(app, host="0.0.0.0", port=7860)